@colebeezley· Jun 23
Marathon exploration on backend
backend
MARATHON
22.7x your typical session
13.7M tokens vs typical 605.9K
13.7Mtokens
110prompts
26:31:42time
1,334lines
Claude Codeclaude-opus-4-8Markdown$266.70
mostly thinking
26h 31m session reading and analyzing the codebase. 13.7M tokens across 110 prompts using claude-opus-4-8.
Reconstructed from session history
Tokens / prompt124.9k
Cost / line$0.200
Cache hit96%
Burn rate$10.05/hr
Derived from this session's token and cost data. Not shown on the feed.
Building 27%Verifying 5%Thinking 57%Delegating 11%
Comments